DER Power Estimation Using Bellwether Asset Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Accurately monitoring and forecasting the performance of distributed energy resources (DER) in electric networks is challenging due to the lack of direct measurements and the difficulty in integrating data from various DER systems, which affects grid operation and planning.
Innovation Solution
A bellwether analysis and forecasting system that uses machine learning to associate measured DER assets with unmeasured ones based on attributes like solar tilt angle, geospatial distance, and other constraints, allowing for power output estimation and forecasting without requiring historical time series data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional methods are used to monitor and forecast DER performance, then direct measurements are required for each asset, but this increases device complexity and monitoring costs
Solution Approach 1:
The patent creates virtual copies (surrogate assets) of unmeasured DER assets by matching them with measured assets based on geographic, technical, and operational attributes. These surrogate assets replicate the performance characteristics of unmeasured assets, enabling forecasting without direct measurements. The matching process creates a mapping relationship where measured assets serve as proxies for their unmeasured counterparts, resolving the contradiction between measurement precision and device complexity.
Solution Approach 2:
The patent introduces surrogate assets as intermediaries between measured and unmeasured DER assets. These intermediaries transfer performance data from measured assets to unmeasured assets through attribute-based matching. The surrogate assets act as mediators that enable information flow without requiring direct measurement infrastructure at every asset location, thereby reducing monitoring system complexity while maintaining forecasting accuracy.
2Measurement precision
If extensive historical time series data is collected for each DER asset, then forecasting accuracy improves, but data acquisition complexity and storage requirements increase
Solution Approach 1:
The patent merges data requirements across multiple unmeasured assets by using a single measured asset as a surrogate for multiple unmeasured assets with similar attributes. Instead of collecting separate historical time series data for each unmeasured asset, the system consolidates data collection to only the measured assets, then applies the collected data to all matched surrogate assets. This merging approach maintains forecasting accuracy while dramatically reducing data acquisition complexity and storage requirements.
3Measurement precision
If individual monitoring of each DER asset is implemented, then measurement precision improves, but the quantity of monitoring equipment and costs increase
Solution Approach 1:
The patent makes measured assets universal by using them to represent multiple unmeasured assets through attribute-based matching. A single measured asset serves multiple functions: it provides data for its own performance monitoring and simultaneously serves as a surrogate for multiple unmeasured assets with similar characteristics. This multi-functionality reduces the total number of measurement devices needed while maintaining monitoring precision across the entire DER portfolio.
Data Source
AI summary
A system for predicting performance of electric power generation and delivery systems is provided. The system includes a computing device including at least one processor in communication with at least one memory. The at least one processor is programmed to store a first plurality of attribute data for a plurality of measured assets attached to a grid, store a plurality of constraints for matching measured assets to unmeasured assets, receive a second plurality of attribute data for an unmeasured asset attached to the grid, compare the first plurality of attribute data to the second plurality of attribute data and the plurality of constraints associated with the unmeasured asset, determine a measured asset of the plurality of measured assets to assign to the unmeasured asset based on the comparison, and determine a performance forecast for the unmeasured asset based on a power performance of the determined measured asset.